HuggingFaceTB/SmolVLM2-256M-Video-Instruct download history

HuggingFaceTB/SmolVLM2-256M-Video-Instruct is a 256M-parameter image text to text model by HuggingFaceTB. In the last 30 days it was downloaded 42,686 times (9,785 in the last 7 days), and 2,215,641 times in total.

It ranks #4,074 on the Hub by monthly downloads and #521 among image text to text models.

It has 115 likes.

It is a quantization of HuggingFaceTB/SmolVLM-256M-Instruct.

25 models build on SmolVLM2-256M-Video-Instruct: 13 quantized, 9 fine-tuned, 3 adapters and 0 merges. Together with the original they were downloaded 53,833 times in the last 30 days. See the SmolVLM2-256M-Video-Instruct galaxy.

Most downloaded derivatives

Open HuggingFaceTB/SmolVLM2-256M-Video-Instruct on Hugging Face